Underwater floor pattern matching with an unmanned underwater vehicle

Abstract

The localization of unmanned underwater vehicle (UUV) is important for the UUV to inspect or manipulator objects. We assume that there is an UUV with a camera sensor and the UUV uses the underwater floor pattern for localization. Because the pattern is known beforehand, the pattern matching between the pattern image and the camera image lets the UUV know its position. The pattern matching algorithm uses the Canny edge extraction method and template based image matching method. The optimization of matching ratio generates the optimal position data of the UUV. We use the Particle Filter method for the optimization method. The experiments show that even though the candidate positional data is not correct, our proposed method finds the position of the UUV with high accuracy.